2001612 - 13.13 - 2.45% speedometer Angular2-TypeScript-TodoMVC/CompletingAllItems/Async / speedometer3 TodoMVC-React-Redux/CompletingAllItems/Sync + 12 more (Windows) regression on Tue November 18 2025

Status: RESOLVED FIXED

(Core :: Graphics: WebRender, defect)

Description

[Treeherder Bug Filer]

Perfherder has detected a browsertime performance regression from push 6b7aa60a1fd5905122b807e0753d1ed671607483. As author of one of the patches included in that push, we need your help to address this regression.

Please acknowledge, and begin investigating this alert within 3 business days, or the patch(es) may be backed out in accordance with our regression policy. Our guide to handling regression bugs has information about how you can proceed with this investigation.

If you have any questions or need any help with the investigation, please reach out to [e-mail]. Alternatively, you can find help on Slack by joining #perf-help, and on Matrix you can find help by joining #perftest.

Regressions:

Ratio	Test	Platform	Options	Absolute values (old vs new)	Performance Profiles
13%	speedometer Angular2-TypeScript-TodoMVC/CompletingAllItems/Async	windows11-64-24h2-nightlyasrelease	fission webrender	1.05 -> 1.19	Before/After
12%	speedometer3 TodoMVC-WebComponents/CompletingAllItems/Async	windows11-64-24h2-nightlyasrelease	fission webrender	2.53 -> 2.84	Before/After
9%	speedometer3 TodoMVC-Svelte-Complex-DOM/DeletingAllItems/Async	windows11-64-24h2-nightlyasrelease	fission webrender	2.83 -> 3.08	Before/After
8%	speedometer3 TodoMVC-Lit-Complex-DOM/DeletingAllItems/Async	windows11-64-24h2-nightlyasrelease	fission webrender	3.56 -> 3.86	Before/After
8%	speedometer3 TodoMVC-Vue/DeletingAllItems/Async	windows11-64-24h2-nightlyasrelease	fission webrender	2.69 -> 2.90	Before/After
8%	speedometer3 TodoMVC-JavaScript-ES5/DeletingAllItems/Sync	windows11-64-24h2-nightlyasrelease	fission webrender	4.87 -> 5.24	Before/After
7%	speedometer Vanilla-ES2015-TodoMVC/Adding100Items/Async	windows11-64-24h2-nightlyasrelease	fission webrender	1.94 -> 2.08	Before/After
7%	speedometer3 TodoMVC-JavaScript-ES5/DeletingAllItems/total	windows11-64-24h2-nightlyasrelease	fission webrender	5.40 -> 5.78	Before/After
7%	speedometer Vanilla-ES2015-Babel-Webpack-TodoMVC/Adding100Items/Async	windows11-64-24h2-nightlyasrelease	fission webrender	1.97 -> 2.10	Before/After
4%	speedometer VanillaJS-TodoMVC/DeletingAllItems	windows11-64-24h2-nightlyasrelease	fission webrender	3.82 -> 3.97	Before/After
4%	speedometer3 perfstats-MinorGC	windows11-64-24h2-nightlyasrelease	fission webrender	447.50 -> 463.36	Before/After
3%	speedometer3 Charts-observable-plot/Stacked by 20/Sync	windows11-64-24h2-nightlyasrelease	fission webrender	15.39 -> 15.79	Before/After
3%	speedometer3 TodoMVC-React-Complex-DOM/CompletingAllItems/Sync	windows11-64-24h2-nightlyasrelease	fission webrender	10.49 -> 10.76	Before/After
2%	speedometer3 TodoMVC-React-Redux/CompletingAllItems/Sync	windows11-64-24h2-nightlyasrelease	fission webrender	13.68 -> 14.01	Before/After

Improvements:

Ratio	Test	Platform	Options	Absolute values (old vs new)	Performance Profiles
24%	speedometer3 TodoMVC-Vue/CompletingAllItems/Sync	windows11-64-24h2-nightlyasrelease	fission webrender	1.64 -> 1.25	Before/After
22%	speedometer3 TodoMVC-Preact-Complex-DOM/DeletingAllItems/Sync	windows11-64-24h2-nightlyasrelease	fission webrender	1.03 -> 0.81	Before/After
19%	speedometer3 TodoMVC-Svelte-Complex-DOM/DeletingAllItems/Sync	windows11-64-24h2-nightlyasrelease	fission webrender	1.14 -> 0.92	Before/After
17%	speedometer3 TodoMVC-Svelte-Complex-DOM/CompletingAllItems/Sync	windows11-64-24h2-nightlyasrelease	fission webrender	1.31 -> 1.09	Before/After
17%	speedometer Preact-TodoMVC/DeletingItems/Sync	windows11-64-24h2-nightlyasrelease	fission webrender	0.84 -> 0.70	Before/After
...	...	...	...	...	...
3%	speedometer EmberJS-TodoMVC/CompletingAllItems	windows11-64-24h2-nightlyasrelease	fission webrender	30.28 -> 29.34	Before/After

Details of the alert can be found in the alert summary, including links to graphs and comparisons for each of the affected tests.

If you need the profiling jobs you can trigger them yourself from treeherder job view or ask [e-mail] to do that for you.

You can run all of these tests on try with ./mach try perf --alert 47496

The following documentation link provides more information about this command.

Comment 1

[BugBot [:suhaib / :marco/ :calixte]]

Set release status flags based on info from the regressing bug 2000149

Comment 2

[BugBot [:suhaib / :marco/ :calixte]]

The bug is marked as tracked for firefox147 (nightly). We have limited time to fix this, the soft freeze is in 10 days. However, the bug still isn't assigned.

:bhood, could you please find an assignee for this tracked bug? Given that it is a regression and we know the cause, we could also simply backout the regressor. If you disagree with the tracking decision, please talk with the release managers.

For more information, please visit BugBot documentation.

Comment 3

[Sotaro Ikeda [:sotaro]]

The subtests has many regressions and improvements. The total scores of sp and sp3 were kept almost the same.

https://perf.compare/compare-results?baseRev=f52d0136b8d82861a34eaf192f2767762cfa639e&baseRepo=try&newRev=c5eb39213442c9994cb98822f1c7998554132b60&newRepo=try&framework=13

Comment 4

[Sotaro Ikeda [:sotaro]]

Close as WONTFIX from comment 3.

Comment 5

[Jeff Muizelaar [:jrmuizel]]

(In reply to Sotaro Ikeda [:sotaro] from comment #3)

The subtests has many regressions and improvements. The total scores of sp and sp3 were kept almost the same.

https://perf.compare/compare-results?baseRev=f52d0136b8d82861a34eaf192f2767762cfa639e&baseRepo=try&newRev=c5eb39213442c9994cb98822f1c7998554132b60&newRepo=try&framework=13

When I look at the graphs on that page it seems like a clear regression to me.

If we're going to regress we should try to have a theory of why and understand what the trade offs are.

The only thing I recall seeing about the advantages was this message from Glenn:
We have initial measurements only from the prototype (where we saw ~20% savings in power usage during video playback). We haven't measured with the merged implementation yet.

We should at least have something more concrete if we're going to accept the regression.

Comment 6

[Sotaro Ikeda [:sotaro]]

OK, then it seems better to backout Bug 2000149.

Comment 7

[Sotaro Ikeda [:sotaro]]

I am going to also check the video playback power usage. But before doing it, bug 1972954 needs to be addressed at first.

Comment 8

[Dianna Smith [:diannaS]]

fixed by backout